Smart Mirror for Smart Life

Muhammad Mu’izzudeen Yusri1, Shahreen Kasim1, Rohayanti Hassan2, Zubaile Abdullah1

Husni Ruslai3, Kamaruzzaman Jahidin4, Mohammad Syafwan Arshad4
Soft Computing and Data Mining Centre, Fakulti Sains Komputer dan Teknologi Maklumat,
1

Universiti Tun Hussein Onn Malaysia, Johor, Malaysia

2
Faculty of Computing, Universiti Teknologi Malaysia,
Johor, Malaysia
3GATES IT Solution Sdn Bhd, Lot 4, Kompleks Usahawan Teknologi MARA, Industrial Centre,

Technovation Park UTM, Jalan Pontian Lama, 81300 Skudai, Johor Darul Ta’zim.
4Powernode Solution Sdn Bhd, 33B, Jalan Kota Raja F27/F Hicom Town Centre, Seksyen 27, Shah Alam,

40400, Shah Alam, Selangor

Corresponding author: shahreen@uthm.edu.my

Abstract— Internet of Things (IoT) is a concept where an
object having the ability to transfer data over a network without the
need for human interaction to human or human to computer. IoT is
known for its advantage that can help simplify people's everyday
routine. Hence, the researcher comes with a proposed system
called Smart Mirror. It is a concept of smart home-based Internet
of Things (IoT). This system allows users to access information
and also control the lights in the house. Relevant information can
be traced such as time and date, weather, warning, traffic, and
location map. The system applies Sonus technology as a medium
of interaction between people and systems. So, users need to
provide instructions to the system orally to acquire the system’s
response. The methodological approach used in this project is The
Evolutionary Prototyping which gathers all requirements and
designs the system in a quick method. A prototype is built to
evaluate and deliver feedback. Improvements will be made to
enhance the prototype, catering to user’s satisfaction. Sonus is a
speech to text library that can quickly and easily add a VUI (Voice
User Interface) to any hardware or software project. Similar to
Alexa, Google Now, and Series, Sonus can always provide
listening function offline for a customizable hotword. Once a
hotword is detected, it will be streamed to user’s speech
recognition cloud service, then the results shall be received. With
Smart Mirror system, users can manage their daily activities at
ease as well as solving many problems in managing some house
chores.
Keywords—smart mirror; smart home; Internet of Things
I. INTRODUCTION
Internet of Things (IoT) is a term used to describe
“technologies, systems, and design principles associated
with the emerging wave of Internet-connected things that
are based on the physical environment” [1]. It refers to a
network of uniquely identifiable things (objects) and their
virtual representations in an Internet-like structure, which
are able to collect and exchange data and are remotely
controlled across existing network infrastructure [2, 3, 4]. It
comprises of major components including sensing function,
heterogeneous access, information processing, security,
privacy, and applications and services.
According to the International
Telecommunication Union (2013), the term Internet of
Things (IoT) is defined as a global structure for society that
enables Internet service to connect to physical matter based
on information and communication technologies available.
IoT is also seen in a broader perspective and nonetheless
brings quite a huge implication of technology on society [5].
Along with the development of technology,
various information can be found easily and the emergence
of the concept of Smart Mirror Smart Home has become
increasingly widespread. The Smart Mirror system which is
based on the concept of Internet of Things (IoT) is
developed specifically to allow users to manage and control
house appliances through voice recognition.
In this case, managing house appliances has been
identified as the main problem faced by most people. There
are just too many things to be done at one time and at
certain point, users are not able to multitask such daunting
chores. For example, when a to-do-list with a number of
house chores has been recorded on a paper, but the paper is
lost because it is misplaced. Another example is when users
are too busy managing their daily activities until some
trivial-yet-critical things are forgotten such as switching off
the lights in a room, which can eventually lead to energy
wastage.
To deal with this situation, Smart Mirror is
developed to provide convenience for users in managing
things and control the usage of electrical appliances in the
house with network connection between the lamp and the
device. Users are required to give instructions to the system
orally, and the system’s sensors will recognize the voice of

978-1-5090-6255-3/17/$31.00 ©2017 IEEE

the consumer to receive instructions and respond to users’ E. User Interface system
needs.
The proposed system is developed based on three
objectives:
1. To design a prototype Smart Mirror using Raspberry PI
2. To develop a voice recognition system to facilitate the
implementation of Smart Mirror.
3. To carry out the testing process on Raspberry PI for
usability evaluation to users.
II. SYSTEM IMPLEMENTATION
This chapter explains the methodology selected in
completing this project. A methodology in this context
refers to the splitting of development work to distinct phases
containing activities with the goal of a better planning and
management [6]. The Methodology approach used in this
Figure 2. Main Display of Smart Mirror.
project is called The Evolutionary Prototyping. Prototype
model is a life-cycle model that allows applications to be
developed in stages so that it can be modified easily
according to feedback from users [7]. Evolutionary
prototyping focuses on gathering a correct and consistent set
of requirements. The process lends particular strength to
building quality software by means of the ongoing
clarification of existing requirements and the discovery of
previously missing or unknown requirements. Traditionally,
the iterative reexamination of a system’s requirements has
not been the panacea that practitioners sought, due to the
predisposition for requirements to creep over and the
difficulty in managing such requirements [8]. Figure 1
shows a flow chart of the system implementation in Smart
Mirror. Users can give instructions to the system to view a
list of commands that are available. Then, they can give
commands via voice instructions provided. Figure 2 to
Figure 8 present the main interfaces available in Smart
Mirror.

Figure 3. List of instructions to be selected by user.

Figure 1. Flowchart of Smart Mirror.

 Figure 6. Main display of the web-based interface. The ‘Speak!’
button is provided for users to issue a voice command.

Figure 4. Example of the system’s response when the user gives

instruction to get location map.

Figure 7. Example of the system’s response when the user gives

instruction to create reminder.

Figure 8. Various function settings are provided.

III. SYSTEM TESTING

A group of developers have conducted several tests on the
Figure 5. Example of the system’s response when the user gives system to ensure that the system meets the functional
instruction to create reminder. requirements. There are three sections involved in the
testing phase, which are test cases, expected results and
F. Web-based User Interface actual results. The term "Success" and "Fail" indicates
whether the field has performed well or resorted into failure.
To implement and test the developed system, Google
Chrome has been selected as the web browser. Developers
have tested the system using unit testing method, starting
from the design of webpage to the system’s functions. Unit
testing was the selected technique as it can help in isolating
bugs. Table I shows the results of unit testing carried out by
the developers.
 TABLE I. UNIT TESTING RESULTS The tests involved were divided into unit testing
and system testing. After the unit testing was carried out on
Actual Smart Mirror, with one-time evaluation, there were no
Test Case Expected Result
Result problems encountered in terms of webpage design where it
Design of webpage Display content in correct is found clean and easy to view, text boxes and text areas
is clean and easy to order, user can clearly Success are able to capture the data entered and different types of
view understand. data can be entered including negative number, positive
Text box and text number, and special characters.
area are able to Data can be entered Meanwhile, in system testing, the evaluation
Success
capture the data successfully. criteria include running the system, configure the PI,
entered configure the sound, configure the voice and control the
System’s validation lights and allow enabling motion detection. This test was
function is able to performed twice and the results are shown in Table II. The
Different types of
validate the input data first test was performed with two test cases resorted into
data are entered
according to the criteria failure, i.e. configuring the voice and controlling the lights
including negative
set in the input element Success and allow enabling motion detection. After some
number, positive
of user interface. System maintenance, the test was performed for the second time.
number, and special
is able to alert user on The second test presented improved results where all
characters
wrongly entered data functions of the system worked properly.
type.
IV. Conclusion
Table II shows the results of system testing. This testing
method was selected for testers to evaluate the system’s As a conclusion, the application is the new technology for
functional criteria.
smart life. From the result testing, most of the function of
the application are functioning well and there still need
some improvement to the development of the newest
functionality on smart mirror. This system could be
enhanced by referring to various other systems and
TABLE II. SYSTEM TESTING RESULTS applications available such as [9-14].

Actual Actual ACKNOWLEDGEMENT

Test Case Expected Result Result Result This research was supported by Universiti Teknologi
(1) (2) Malaysia under Vot No. 11H84.

Running the • Running Smart References

Success Success
system Mirror [1] Holler J., Tsiatsis V., Mulligan C., Avesand S., Karnouskos
S., Boyle D.M2M to IoT—the vision: from M2M to IoTFrom
• Rotate monitor Machine-to-Machine to the Internet of Things: Introduction to
• Disable a New Age of Intelligence20141stchapter 2, section
2.2Oxford, UKAcademic Press1418 Google Scholar
screensaver and
[2] Chen M., Wan J., Li F.Machine-to-machine communications:
Configure remove panel architectures, standards and applicationsKSII Transactions on
Success Success
PI • Hide the mouse Internet and Information
during inactive Systems20126248049710.3837/tiis.2012.02.0022-s2.0-
84861022395 Google Scholar CrossRef
mode
[3] Internet of Things Global Standards Initiative2015Geneva,
SwitzerlandITU: Committed to connecting the world
• Audio input and [4] Williams J.Internet of Things: Science Fiction or Business
Configure
output Success Success Fact?Harvard Business Review Analytic Services Report,
sound December 2014
configuration
• Setting up [5] International Telecommunication Union (2013). Harnessing
Configure the Internet of Things for Global Development.
Speech Fail Success https://www.itu.int/en/action/broadband/Documents/Harnessi
voice
Recognition ng-IoT-Global-Development.pdf
Control [6] Centers for Medicare & Medicaid Services (CMS) Office of
lights and • ConfigUI to Information Service (2008). Selecting A Development
allow configure and Approach. Retrieved on October 27, 2016 from
Fail Success www.cms.gov/Research-Statistics-Data-and-Systems/CMS-
Enabling enable motion Information-
Motion detection Technology/XLC/Downloads/SelectingDevelopmentApproac
Detection h.pdf
[7] Ian Sommerville (2007). Software Engineering. 8th ed.
United States: Pearson Education, Inc.
[8] R. A. Carter, A. I. Anton, A. Dagnino and L. Williams,
"Evolving beyond requirements creep: a risk-based
evolutionary prototyping model," Proceedings Fifth IEEE
International Symposium on Requirements Engineering,
Toronto, Ont., 2001, pp. 94-101.
[9] Kasim, S., Hafit, H., Yee, N. P., Hashim, R., Ruslai, H., Jahidin, K.,
& Arshad, M. S. (2016, November). CMIS: Crime Map Information
System for Safety Environment. In IOP Conference Series: Materials
Science and Engineering (Vol. 160, No. 1, p. 012096). IOP
Publishing.
[10] Kasim, S., Hafit, H., Leong, T. H., Hashim, R., Ruslai, H., Jahidin,
K., & Arshad, M. S. (2016, November). SRC: Smart Reminder Clock.
In IOP Conference Series: Materials Science and Engineering (Vol.
160, No. 1, p. 012101). IOP Publishing.
[11] Kasim, S., Hafit, H., Juin, K. P., Afif, Z. A., Hashim, R., Ruslai, H.,
... & Arshad, M. S. (2016, November). BBIS: Beacon Bus
Information System. In IOP Conference Series: Materials Science and
Engineering (Vol. 160, No. 1, p. 012097). IOP Publishing.
[12] Kasim, S., Xia, L. Y., Wahid, N., Fudzee, M. F. M., Mahdin, H.,
Ramli, A. A., ... & Salamat, M. A. (2016, August). Indoor Navigation
Using A* Algorithm. In International Conference on Soft Computing
and Data Mining (pp. 598-607). Springer, Cham.
[13] Kasim, S., Azahar, U. A., Samsudin, N. A., Fudzee, M. F. M.,
Mahdin, H., Ramli, A. A., & Suparjoh, S. (2016, August). E-Code
Checker Application. In International Conference on Soft Computing
and Data Mining (pp. 570-578). Springer, Cham.
[14] Mahdin, H., Senan, N., Kasim, S., Ibrahim, N., & Abdullah, N. A.
(2014). Teaching computer programming to IPAD generation.